llama-3-nectar-dpo-8B: benchmark results
Provider: Meta. Released 2024-05-14. Access: Open.
Unified ELO 1472 ± 1, rank #832 of 1392 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - GSM8K | 49.05 | Accuracy (%) | 63.9 |
| Open Korean LLM Leaderboard | 38.18 | Average Score (%) | 63 |
| Open Chinese LLM - C-Eval Semantic | 69.02 | Accuracy (%) | 48.4 |
| Open Chinese LLM - CMMLU | 53.06 | Accuracy (%) | 46.9 |
| Open Chinese LLM Leaderboard | 55.27 | Average Score (%) | 39.2 |
| Open Chinese LLM - TruthfulQA MC | 52.54 | Accuracy (%) | 38 |
| Open Chinese LLM - ARC Challenge | 48.89 | Accuracy (%) | 36.8 |
| Open Chinese LLM - WinoGrande | 61.48 | Accuracy (%) | 28 |
| Open Chinese LLM - HellaSwag | 52.86 | Accuracy (%) | 12.8 |
Interactive version: theaggregate.ai/model?slug=llama-3-nectar-dpo-8b · How It Works · Data refreshed daily, snapshot 2026-09-05.